Abstract | ||
---|---|---|
Deep Neural Networks (DNNs) are often criticized because they lack the ability to learn more than one task at a time: Multitask Learning is an emerging research area whose aim is to overcome this issue. In this work, we introduce the Pareto Multitask Learning framework as a tool that can show how effectively a DNN is learning a shared representation common to a set of tasks. We also experimentally show that it is possible to extend the optimization process so that a single DNN simultaneously learns how to master two or more Atari games: using a single weight parameter vector, our network is able to obtain sub-optimal results for up to four games. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1007/978-3-030-37599-7_50 | MACHINE LEARNING, OPTIMIZATION, AND DATA SCIENCE |
Keywords | Field | DocType |
Multitask learning, Neural and evolutionary computing, Deep neuroevolution, Hypervolume, Kullback-Leibler Divergence, Evolution Strategy, Deep artificial neural networks, Atari 2600 Games | Mathematical optimization,Multi-task learning,Computer science,Pareto principle | Conference |
Volume | ISSN | Citations |
11943 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Deyan Dyankov | 1 | 0 | 0.34 |
Salvatore Danilo Riccio | 2 | 0 | 0.34 |
Giuseppe Di Fatta | 3 | 529 | 39.23 |
Giuseppe Nicosia | 4 | 0 | 1.69 |